Fig. 1From: VirSorter2: a multi-classifier, expert-guided approach to detect diverse DNA and RNA virusesOverview of the VirSorter2 framework. Schematic of the viral prediction pipeline used in VirSorter2. âhmmDBâ represents databases of HMM profiles including viral HMMs from Xfam (described in the âMethodsâ section) and viral protein families (VPF) from JGI Earthâs Virome [17], and cellular HMMs (archaeal, bacterial, eukaryotic) as well as âmixedâ HMMs (not specific to either virus or cellular organisms) from Pfam [43]. A default cutoff of 30 is used for the HMM searches. âClassifiersâ refers to random forest classifiers trained on known viral genomes and cellular genomes from different viral groups (see âTraining classifiersâ section in âMethodsâ). The default max score cutoff is set to 0.5Back to article page